Loading...
Loading...
Found 2,503 Skills
Extended `5dive` CLI recipes beyond the everyday core — see the `5dive-cli` skill first for spawning/messaging sibling agents and the basic task queue. Use THIS skill for hiring a ready-made persona off the agent market (`5dive market`, `hire --from-market`) or firing one (`5dive fire`), auth recovery (`error.class=auth_required`, `--defer-auth`, device-code login via `agent auth start/poll/submit`), BYO-provider agents (`--provider`), multi-account auth (`5dive account`), declarative fleets and company templates (`5dive up/down/ps/export`, `team import`), hosting a CrewAI crew (`5dive crew`), controlling agents on OTHER registered boxes (`5dive fleet`), recurring/scheduled work (`task add --recurring`, `5dive heartbeat`) and projects (`5dive project add`), building or editing multi-agent loops — a relay with optional human gates (`task loop start`) or a maker→verifier review loop (`task add --verifier`, `task reject`, `5dive loop` LOOP-7 verbs) — decomposing an outcome into a guardrailed task DAG (`5dive goal add`) or a self-steering objective bound to a live metric (`5dive objective`), compiling durable knowledge into the shared wiki (`5dive memory add`), org-chart writes (`5dive org set`), convening a governance vote (`5dive council`), reading fleet health / token burn / the daily standup (`5dive supervisor`, `5dive usage`, `5dive digest`), a machine-readable health check (`5dive doctor --json`, `5dive selfcheck --json`), a task's causal history (`5dive trace`), the current model id per alias (`5dive models`), Telegram/Discord pairing and shared team-bot setup, a delegated GitHub push-for-review (`5dive push`), or the onboarding wizard (`5dive company`).
Spawn parallel adversarial subagents that DRIVE THE REAL SYSTEM (not reason from source) to break new code before it ships — schemas, contracts, parsers, serializers, protocols, state machines, security/redaction, freeze guards. Use as a standard step on any nontrivial feature/task once the implementation is green and BEFORE the final convergence (dootsabha) review. Each agent gets one disjoint attack surface + a "try to break X" charter; every finding is independently reproduced before it is believed, then fixed with a regression test. Trigger phrases include "adversarial review", "try to break this", "find the bugs I missed", "harden before done", "attack this schema/parser/contract", and the shux feature-protocol adversarial step.
Score text from -1 (strongly negative) to +1 (strongly positive) with a label, handling negation, intensifiers and emphasis. Called as POST /v1/text/sentiment, it takes text and returns score, label, matches, positiveTerms. A support-triage or review-monitoring agent must decide whether a message is a complaint before it routes or escalates it, and a model call for one number costs more than this and is not reproducible. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
Know a company completely. Opens by asking your goal and where your context lives (CRM? call recorder? team chat? email?), then routes to 4 modes - account deep-dive & plan (external + your internal history with them), org chart (who runs it), tech stack & wedge, competitive battlecard. Use for "tell me about <company>", "account plan for <company>", "org chart for <company>", "what's their tech stack", "battlecard for <competitor>", "how do we beat <X>", "research this account".
[user] 명시적인 작업 원천을 저장소 근거와 자연스러운 대화로 구체화해, 새 세션이나 더 낮은 수준 실행자가 원 대화 없이 사용할 수 있는 `.tigerkit/seed.md`를 준비합니다.
[user/auto] 하나의 pull request의 review feedback 또는 지원 가능한 GitHub Actions 실패를 fresh state로 읽고, 자연스러운 해결 계획을 합의한 뒤 필요 시 `seed.md`를 사용해 수정·검증·제한된 publication까지 처리합니다.
[user/auto] 하나의 observed 또는 measured Agent Skill anomaly를 fresh context에서 재현·격리한 뒤, 검증된 skill objective를 tk-learn으로 라우팅한다. selection, instruction, output, host, eval, stability 또는 resource incident에 사용한다. ordinary code bug, static audit, new skill creation 또는 symptom-free optimization에는 사용하지 않는다.